| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.2207527975584944, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 4.7996, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 3.018367290496826, | |
| "eval_runtime": 230.2288, | |
| "eval_samples_per_second": 8.127, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0002968954812004139, | |
| "loss": 2.0295, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 0.71845942735672, | |
| "eval_runtime": 234.0394, | |
| "eval_samples_per_second": 7.994, | |
| "eval_wer": 0.5917076167076167, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0002927561228009658, | |
| "loss": 0.4632, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 0.4624195396900177, | |
| "eval_runtime": 419.7523, | |
| "eval_samples_per_second": 4.457, | |
| "eval_wer": 0.4606879606879607, | |
| "step": 1200 | |
| } | |
| ], | |
| "max_steps": 29490, | |
| "num_train_epochs": 30, | |
| "total_flos": 6.668424512230441e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |